150 likes | 264 Views
Microphone Integration – Can Improve ARS Accuracy?. Tom Houy thouy@attglobal.net. Telematics Infotainment Solutions. One Alternative. Wind noise reduction. Anti-echo boom. Improving Voice Quality. Mic positioned a long way away from users mouth.
E N D
Microphone Integration –Can Improve ARS Accuracy? Tom Houy thouy@attglobal.net
One Alternative Wind noise reduction Anti-echo boom
Improving Voice Quality Mic positioned a long way away from users mouth High power speaker positioned close to mic
Noise Considerations ASR Impacts: • Dialog Design • Grammars • Discreet / Continuous • Word / Phrase Non-Impacts: • Languages • Processing Reqts • Memory
Hands Free Considerations Acoustic Echo Cancellation • Effect on far end speech recognition • Echo Return Loss • Capability to handle speaker distortion • Ability to adapt to changing Acoustic environment • Varied Acoustic Coupling • Beating with other echo cancellers • Double Talk • Barge In
Hands Free Considerations Noise Suppression • SNR improvement • Distortion • Interaction with vocoder • Voice Quality • Time to Converge • Noise types • Ability to adapt to acoustic environmental factors • Automatic Gain Control • Microphone Interaction
Algorithms Must Mimic Human Processing How humans hear How ASR engines hear • Sound pressure is converted to electrical waves by the microphone • Electrical waves are converted to a digital representation (numbers) by the analog to digital converter • The numbers are processed into frequency components which are analogous to the output of the cochlea • The independent frequency components are subjected to temporal analysis and correlated to distinguish speech from noise • Speech is extracted from the noisy signal for subsequent processing A/D Component Extraction Independent Component Analysis • Sound waves cause the ear drum to vibrate in the middle ear • Vibration in the middle ear is translated into fluid motion in the cochlea • The hair cells in the inner ear vibrate in a unique pattern corresponding to the frequency spectrum characteristic of the incoming sound • The motion of each hair is converted to electrical pulses which are transmitted to the brain • The brain separates speech from other sound components for analysis Voice Extraction
Algorithms Enable Superior Noise Suppression Voice Extraction The voice extractor modifies each frequency component according to the voice and noise model. The Voice Extractor takes advantage of psychoacoustics principals to minimize noise floor artifacts and perceived voice distortion Component Extraction Voice Extraction Synthesis Synthesis The extracted voice components are recombined and converted into the time domain Component Extraction The audio signal is converted to the frequency domain and partitioned according to critical voice components Voice Component Analysis Voice Analysis The voice analysis block considers temporal and correlative properties of speech and noise to develop a predictive model of the speech components
Algorithms Enable Natural Conversation • Algorithmscreate a new approach to Acoustic Echo Cancellation Rx D/A Subband Adaptive Filter Uses CSR Detroit’s Proprietary Restored Estimator Reutilization method to quickly model the linear transfer function between the reference signal and the microphone. Allows for rapid and more accurate plant estimation Subband Adaptive Filter Near End F3 Residual Echo Canceller Tx Programmable Non-Linear Processing Environment Restoration A/D F3 Residual Echo Cancellation Uses proprietary estimation methods to improve Echo Return Loss introducing speech degradation
One Alternative Wind noise reduction Anti-echo boom
But the real mass market is still in the future…. What will make headsets attractive to everyone for the auto? • Work with any phone • Batteries last 8 hours (longer for stereo) • Looks nice • Great sound quality (at least as good as the phone) • Natural to use • Not too expensive • Noise Suppression
DSPs enhance Bluetooth • Bluetooth Multimedia devices were launched more than 2 years ago and has more than 10MU • Next step: More powerful Bluetooth Multimedia; realising the vision
Name announcing – improving safety • With name announcing Bluetooth headsets can contribute further to road safety Eyes stay on the road John Smith calling